In [9]:
#read in the files
for xx in range(1,11):
#change the file name at 10
ns = 'I0'
if xx == 10:
ns = 'I'
for y in range(1,5):
for z in range(0,10):
#check if path existed
if os.path.exists(ns+str(xx)+'R'+str(y)+'V'+str(z)+'.CSV'):
# Read the csv files and naming its columns
df = pd.read_csv(ns+str(xx)+'R'+str(y)+'V'+str(z)+'.CSV',
names=
['Day_of_Year',
'UTC_Hours',
'UTC_Minutes',
'UTC_seconds',
'IOP_number',
'van_number',
'pass_number',
'hours_in_CDT_day_start',
'latitude',
'longitude',
'altitude',
'number_of_satellites',
'hdop',
'concentration_of_SF6',
'QC_flag'])
# generate release Dataframe dff based on the first csv
# generate a new columns that record the experiment in mins
# eliminate the moving van data
if z == 5:
continue
# generate a new column and concat it to dff
else:
k = df['hours_in_CDT_day_start'][0]
df['Time_in_mins'] = df['hours_in_CDT_day_start'].apply(lambda x: (x-k)*60)
df['cleaned_concertration'] = df['concentration_of_SF6'].apply(lambda x: x+999)
if (df['cleaned_concertration']==0).all():
continue
# see if gps position change: if latitude, longitude, altitude stays the same
la = (df['latitude']==df['latitude'][0]).all()
lo = (df['longitude']==df['longitude'][0]).all()
al = (df['altitude']==df['altitude'][0]).all()
if la and lo and al == False:
continue
else:
# clean the concentration_of_SF6 data and create a new dataframe to be plot
df1 = df[['cleaned_concertration','Time_in_mins']].copy()
# calculate the moving averge with a with of 200
df1['SMA200'] = df1['cleaned_concertration'].rolling(200).mean()
df1.dropna(inplace = True)
# plot the graph
plt.figure(figsize=(20,5))
plt.plot(df1['Time_in_mins'],df1['cleaned_concertration'],label = 'concentration_of_SF6')
plt.plot(df1['Time_in_mins'],df1['SMA200'],label = 'SMA200')
# label the graph
plt.xlabel('Time_in_mins')
plt.ylabel('concentration_of_SF6')
plt.legend()
plt.title('I0'+str(xx)+'R'+str(y)+'V'+str(z)+'.CSV')
plt.show()
# if path not exist, continue
else:
continue
